@inproceedings{yu-etal-2020-dataset,
title = "Dataset and Enhanced Model for Eligibility Criteria-to-{SQL} Semantic Parsing",
author = "Yu, Xiaojing and
Chen, Tianlong and
Yu, Zhengjie and
Li, Huiyu and
Yang, Yang and
Jiang, Xiaoqian and
Jiang, Anxiao",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.714/",
pages = "5829--5837",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Clinical trials often require that patients meet eligibility criteria (e.g., have specific conditions) to ensure the safety and the effectiveness of studies. However, retrieving eligible patients for a trial from the electronic health record (EHR) database remains a challenging task for clinicians since it requires not only medical knowledge about eligibility criteria, but also an adequate understanding of structured query language (SQL). In this paper, we introduce a new dataset that includes the first-of-its-kind eligibility-criteria corpus and the corresponding queries for criteria-to-sql (Criteria2SQL), a task translating the eligibility criteria to executable SQL queries. Compared to existing datasets, the queries in the dataset here are derived from the eligibility criteria of clinical trials and include \textit{Order-sensitive, Counting-based, and Boolean-type} cases which are not seen before. In addition to the dataset, we propose a novel neural semantic parser as a strong baseline model. Extensive experiments show that the proposed parser outperforms existing state-of-the-art general-purpose text-to-sql models while highlighting the challenges presented by the new dataset. The uniqueness and the diversity of the dataset leave a lot of research opportunities for future improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2020-dataset">
<titleInfo>
<title>Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaojing</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianlong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengjie</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huiyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqian</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anxiao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Clinical trials often require that patients meet eligibility criteria (e.g., have specific conditions) to ensure the safety and the effectiveness of studies. However, retrieving eligible patients for a trial from the electronic health record (EHR) database remains a challenging task for clinicians since it requires not only medical knowledge about eligibility criteria, but also an adequate understanding of structured query language (SQL). In this paper, we introduce a new dataset that includes the first-of-its-kind eligibility-criteria corpus and the corresponding queries for criteria-to-sql (Criteria2SQL), a task translating the eligibility criteria to executable SQL queries. Compared to existing datasets, the queries in the dataset here are derived from the eligibility criteria of clinical trials and include Order-sensitive, Counting-based, and Boolean-type cases which are not seen before. In addition to the dataset, we propose a novel neural semantic parser as a strong baseline model. Extensive experiments show that the proposed parser outperforms existing state-of-the-art general-purpose text-to-sql models while highlighting the challenges presented by the new dataset. The uniqueness and the diversity of the dataset leave a lot of research opportunities for future improvement.</abstract>
<identifier type="citekey">yu-etal-2020-dataset</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.714/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5829</start>
<end>5837</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing
%A Yu, Xiaojing
%A Chen, Tianlong
%A Yu, Zhengjie
%A Li, Huiyu
%A Yang, Yang
%A Jiang, Xiaoqian
%A Jiang, Anxiao
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F yu-etal-2020-dataset
%X Clinical trials often require that patients meet eligibility criteria (e.g., have specific conditions) to ensure the safety and the effectiveness of studies. However, retrieving eligible patients for a trial from the electronic health record (EHR) database remains a challenging task for clinicians since it requires not only medical knowledge about eligibility criteria, but also an adequate understanding of structured query language (SQL). In this paper, we introduce a new dataset that includes the first-of-its-kind eligibility-criteria corpus and the corresponding queries for criteria-to-sql (Criteria2SQL), a task translating the eligibility criteria to executable SQL queries. Compared to existing datasets, the queries in the dataset here are derived from the eligibility criteria of clinical trials and include Order-sensitive, Counting-based, and Boolean-type cases which are not seen before. In addition to the dataset, we propose a novel neural semantic parser as a strong baseline model. Extensive experiments show that the proposed parser outperforms existing state-of-the-art general-purpose text-to-sql models while highlighting the challenges presented by the new dataset. The uniqueness and the diversity of the dataset leave a lot of research opportunities for future improvement.
%U https://aclanthology.org/2020.lrec-1.714/
%P 5829-5837
Markdown (Informal)
[Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing](https://aclanthology.org/2020.lrec-1.714/) (Yu et al., LREC 2020)
ACL